ALEXANDRIA, Va., Aug. 18 -- United States Patent no. 12,711,769, issued on Aug. 18, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Language instructed temporal localization in videos" was invented by De-An Huang (Cupertino, Calif.), Shijia Liao (Santa Clara, Calif.), Subhashree Radhakrishnan (Milpitas, Calif.), Hongxu Yin (San Jose, Calif.), Pavlo Molchanov (Mountain View, Calif.), Zhiding Yu (Santa Clara, Calif.) and Jan Kautz (Lexington, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments of the present disclosure relate to language instructed temporal localization in videos, and provide multimodal large language models (LLMs) for performing language instructed temporal localization in v...